Training in progress, epoch 1

README.md

@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 30
+- lr_scheduler_warmup_steps: 200
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 

adapter_config.json

@@ -16,13 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "q_proj",
+    "up_proj",
     "o_proj",
-    "k_proj",
     "gate_proj",
-    "up_proj"
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9b29b82d33a16ab23ea3f1ce9e3fa9c8eb77125061d5c53b6ed9d8cf783cbc3
+oid sha256:9cd983ec4e34e31c66028a370aad768448bf4bf0f3f43f1b29b2cc62e32e9f82
 size 80013120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0801a6eeff3d52765aa1ec4bf24721276bacd85d4998f9d0a8dea2b34ec8afba
+oid sha256:add4c1b8058597a3a6d77d887369a731b4259a245b81f1b1da63f72d6edbb6e5
 size 4600